Nicheloom visits: 58,111 all-time · 7,637 in the last 7 days

The opportunity tracker for new startups.

Today: 1,953 launches · Niche of the day: specialized calculation tools · See what launched today →

Roundtable

A rubber duck that argues with itself

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

Hey HN, I'm a founder at Ovlo a supply chain company.I had a problem. After every batch of customer interviews/research/feedback sessions, I'd run ideas through an LLM to help me decide what we should build next.Except it was obvious to my cofounder I wasn't really validating anything. LLMs are incredibly good at agreeing with you in subtle ways, especially when you feed them context that already reflects your thoughts. I'd ask "Does this make sense?" and get a beautifully worded essay about why yes, obviously, this is the best thing ever.I was using AI as an echo chamber without noticing. It was like a game, you bias the model a little, it biases you a little back.So my cofounder hacked together a tiny internal tool over the weekend to break that loop. Instead of one model validating my thinking, it puts multiple personas with different expertise in the same conversation. They naturally push back on each other.It's basically a rubber duck that argues with itself.We gave it some UI and called it Roundtable: https://roundtable.ovlo.aiWould love to hear what you'all think!

HN · launched Dec 2, 2025 · 6 upvotes (top 73%) · 0 views

Niche: startup idea validation tools · 144 launches, 21 in the last 7 days ▲ +11% · Explore this niche →

Category and tags

  • Horizontal
  • Agent / copilot
  • Developer
  • AI-native
  • Hobby / open-source project

Visit website ↗ Source listing ↗

Could you build this?

Yes It is an LLM wrapper application that sets up multi-agent debate prompts simulating diverse personas to critique ideas.

Discussion

4 comments analyzed.

Competitors mentioned: ChatGPT, General LLMs for ideation/sanity-checking

Concerns raised: LLMs too agreeable and add positive spin even when asked to be critical, Standard LLMs not effective for honest product decision feedback

Feature requests: Add ability to use more than 2 personas in debates

Competitors

Other products that read as similar to this one : 224 launches clear the similarity bar, closest 8 shown.

Attention rank: #181 of 225 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 33 days after the earliest competitor.

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.